{"id":"https://openalex.org/W2903718461","doi":"https://doi.org/10.1109/icassp.2019.8682443","title":"Semi-supervised Monaural Singing Voice Separation with a Masking Network Trained on Synthetic Mixtures","display_name":"Semi-supervised Monaural Singing Voice Separation with a Masking Network Trained on Synthetic Mixtures","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2903718461","doi":"https://doi.org/10.1109/icassp.2019.8682443","mag":"2903718461"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008066329","display_name":"Michael Michelashvili","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Michael Michelashvili","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081028371","display_name":"Sagie Benaim","orcid":"https://orcid.org/0000-0003-0002-3467"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sagie Benaim","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008066329"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":2.322,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8886093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"291","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9357897043228149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7334283590316772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906847953796387},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6487612724304199},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.620928943157196},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5547599792480469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42250046133995056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3463394045829773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21333414316177368},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.190883070230484}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9357897043228149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7334283590316772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906847953796387},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6487612724304199},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.620928943157196},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5547599792480469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42250046133995056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3463394045829773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21333414316177368},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.190883070230484},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1504438288","https://openalex.org/W1594771616","https://openalex.org/W2030781210","https://openalex.org/W2058676219","https://openalex.org/W2065126082","https://openalex.org/W2093492509","https://openalex.org/W2099471712","https://openalex.org/W2118718620","https://openalex.org/W2165685007","https://openalex.org/W2216862344","https://openalex.org/W2296724634","https://openalex.org/W2398306137","https://openalex.org/W2523217490","https://openalex.org/W2587994092","https://openalex.org/W2588200971","https://openalex.org/W2591938218","https://openalex.org/W2593414223","https://openalex.org/W2603777577","https://openalex.org/W2737057113","https://openalex.org/W2787069756","https://openalex.org/W2902662422","https://openalex.org/W2916985722","https://openalex.org/W2917831833","https://openalex.org/W2953368614","https://openalex.org/W2962793481","https://openalex.org/W2963191020","https://openalex.org/W2963376432","https://openalex.org/W2963800363","https://openalex.org/W2963816101","https://openalex.org/W2963890275","https://openalex.org/W2964005873","https://openalex.org/W2964229681","https://openalex.org/W4298310324","https://openalex.org/W4320013936","https://openalex.org/W6666773116","https://openalex.org/W6677759377","https://openalex.org/W6697040288","https://openalex.org/W6712656540","https://openalex.org/W6734097737","https://openalex.org/W6741813933","https://openalex.org/W6745392335","https://openalex.org/W6745457739","https://openalex.org/W6759212570","https://openalex.org/W6766320909"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1964208564","https://openalex.org/W169038075","https://openalex.org/W2401567014","https://openalex.org/W1976239252","https://openalex.org/W1614994442","https://openalex.org/W2035580387","https://openalex.org/W2889698889"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,11,47,58],"problem":[3],"of":[4,17,19,29,112],"semi-supervised":[5,122],"singing":[6,83,114],"voice":[7],"separation,":[8],"in":[9],"which":[10,105],"training":[12,110],"data":[13],"contains":[14],"a":[15,35,43,96],"set":[16,28],"samples":[18,76,111],"mixed":[20,44,75],"music":[21],"(singing":[22],"and":[23,25,116],"instrumental)":[24],"an":[26,54],"unmatched":[27],"instrumental":[30,49,55,68,87],"music.":[31],"Our":[32,89],"solution":[33],"employs":[34],"single":[36],"mapping":[37],"function":[38],"g,":[39],"which,":[40],"applied":[41,52],"to":[42,53],"sample,":[45,56],"recovers":[46],"underlying":[48],"music,":[50],"and,":[51],"returns":[57],"same":[59],"sample.":[60],"The":[61],"network":[62],"g":[63],"is":[64],"trained":[65],"using":[66],"purely":[67],"samples,":[69],"as":[70,72],"well":[71],"on":[73,95],"synthetic":[74],"that":[77,92],"are":[78,94,106,117],"created":[79],"by":[80],"mixing":[81],"reconstructed":[82],"voices":[84],"with":[85,98,109],"random":[86],"samples.":[88],"results":[90],"indicate":[91],"we":[93],"par":[97],"or":[99],"better":[100,118],"than":[101,119],"fully":[102],"supervised":[103],"methods,":[104],"also":[107],"provided":[108],"unmixed":[113],"voices,":[115],"other":[120],"recent":[121],"methods.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
